From: Eric Dumazet <eric.dumazet@gmail.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: Linux Netdev List <netdev@vger.kernel.org>
Subject: [PATCH net-next-2.6] net: Introduce dev_get_by_name_rcu()
Date: Fri, 30 Oct 2009 18:11:27 +0100 [thread overview]
Message-ID: <4AEB1E3F.3010002@gmail.com> (raw)
Some workloads hit dev_base_lock rwlock pretty hard.
We can use RCU lookups to avoid touching this rwlock
(and avoid touching netdevice refcount)
netdevices are already freed after a RCU grace period, so this patch
adds no penalty at device dismantle time.
However, it adds a synchronize_rcu() call in dev_change_name()
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
include/linux/netdevice.h | 1
net/core/dev.c | 49 +++++++++++++++++++++++++++++-------
2 files changed, 41 insertions(+), 9 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 193b637..86773e1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1115,6 +1115,7 @@ extern void __dev_remove_pack(struct packet_type *pt);
extern struct net_device *dev_get_by_flags(struct net *net, unsigned short flags,
unsigned short mask);
extern struct net_device *dev_get_by_name(struct net *net, const char *name);
+extern struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
extern struct net_device *__dev_get_by_name(struct net *net, const char *name);
extern int dev_alloc_name(struct net_device *dev, const char *name);
extern int dev_open(struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 94f42a1..f54d8b8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -213,7 +213,7 @@ static int list_netdevice(struct net_device *dev)
write_lock_bh(&dev_base_lock);
list_add_tail(&dev->dev_list, &net->dev_base_head);
- hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
+ hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
hlist_add_head_rcu(&dev->index_hlist,
dev_index_hash(net, dev->ifindex));
write_unlock_bh(&dev_base_lock);
@@ -230,7 +230,7 @@ static void unlist_netdevice(struct net_device *dev)
/* Unlink dev from the device chain */
write_lock_bh(&dev_base_lock);
list_del(&dev->dev_list);
- hlist_del(&dev->name_hlist);
+ hlist_del_rcu(&dev->name_hlist);
hlist_del_rcu(&dev->index_hlist);
write_unlock_bh(&dev_base_lock);
}
@@ -599,6 +599,32 @@ struct net_device *__dev_get_by_name(struct net *net, const char *name)
EXPORT_SYMBOL(__dev_get_by_name);
/**
+ * dev_get_by_name_rcu - find a device by its name
+ * @net: the applicable net namespace
+ * @name: name to find
+ *
+ * Find an interface by name.
+ * If the name is found a pointer to the device is returned.
+ * If the name is not found then %NULL is returned.
+ * The reference counters are not incremented so the caller must be
+ * careful with locks. The caller must hold RCU lock.
+ */
+
+struct net_device *dev_get_by_name_rcu(struct net *net, const char *name)
+{
+ struct hlist_node *p;
+ struct net_device *dev;
+ struct hlist_head *head = dev_name_hash(net, name);
+
+ hlist_for_each_entry_rcu(dev, p, head, name_hlist)
+ if (!strncmp(dev->name, name, IFNAMSIZ))
+ return dev;
+
+ return NULL;
+}
+EXPORT_SYMBOL(dev_get_by_name_rcu);
+
+/**
* dev_get_by_name - find a device by its name
* @net: the applicable net namespace
* @name: name to find
@@ -614,11 +640,11 @@ struct net_device *dev_get_by_name(struct net *net, const char *name)
{
struct net_device *dev;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_name(net, name);
+ rcu_read_lock();
+ dev = dev_get_by_name_rcu(net, name);
if (dev)
dev_hold(dev);
- read_unlock(&dev_base_lock);
+ rcu_read_unlock();
return dev;
}
EXPORT_SYMBOL(dev_get_by_name);
@@ -960,7 +986,12 @@ rollback:
write_lock_bh(&dev_base_lock);
hlist_del(&dev->name_hlist);
- hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name));
+ write_unlock_bh(&dev_base_lock);
+
+ synchronize_rcu();
+
+ write_lock_bh(&dev_base_lock);
+ hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name));
write_unlock_bh(&dev_base_lock);
ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev);
@@ -1062,9 +1093,9 @@ void dev_load(struct net *net, const char *name)
{
struct net_device *dev;
- read_lock(&dev_base_lock);
- dev = __dev_get_by_name(net, name);
- read_unlock(&dev_base_lock);
+ rcu_read_lock();
+ dev = dev_get_by_name_rcu(net, name);
+ rcu_read_unlock();
if (!dev && capable(CAP_NET_ADMIN))
request_module("%s", name);
reply other threads:[~2009-10-30 17:11 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4AEB1E3F.3010002@gmail.com \
--to=eric.dumazet@gmail.com \
--cc=davem@davemloft.net \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).